Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    country names

    oai_token-act-pair · gpt-3.5-turbo

    countries and geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bryce
    -0.43
    ©¶æ
    -0.41
    æѦ
    -0.40
    wy
    -0.37
    èĢ
    -0.37
    osate
    -0.37
    wang
    -0.36
     Lama
    -0.36
    amy
    -0.35
    stellar
    -0.35
    POSITIVE LOGITS
     depends
    0.38
     uncertainties
    0.35
     paraph
    0.35
    itialized
    0.34
     uncertainty
    0.33
    epad
    0.33
     physic
    0.32
    ixir
    0.31
    ipop
    0.31
    ariat
    0.31
    Act Density 7.350%

    No Known Activations